If you had the chance to go back in time, what would you do differently about your data science journey?

Going back in time is a great way to understand what is it that one needs to do now to change course for the better. I love this trick that makes for great conversations and self-examination.

One thing I will change if I can go back is to spend more time in undergraduate life to pick up technology skills before going to a Masters' program.

I used to code in school, where I learned BASIC in 8th grade and then learned C++ in 11th grade. I continue coding on my own with Perl in undergrad but I could have done more with scientific computing. I should have done more Matlab/Python/R but in 2002 R and Python were not as common as Matlab.

By the time I graduated from undergrad and went to the US for my Masters, I was using R in my graduate studies in a few courses in Data Mining and Statistics. I also used Perl in my thesis work to run a web interface, connect a GAMS solver to a CGI web script and a bunch of other work.

Looking back, I would go back to my undergrad days and pick up a good book on Python development. I would then pick up a few good books on web development during my Masters or take up an online MOOC on Software Development.

While I learned all of this on the job in the last decade, I could have had a lot more fun doing what I did, had I known more concepts and tools.

I also wish I was taking a lot more notes than I actually did back then. I am a huge note taker now. I take notes in physical notebooks, online, on my phone, Evernote etc. I find taking notes a natural extension to the thinking process. And the notes I take to organize my work, those are invaluable assets I revisit from time to time.

So yeah, I'd go back and spend more time on practicing coding, reading more technical books and taking lots of notes.